Weakly supervised object detection~(WSOD) has recently attracted much attention. However, the lack of bounding-box supervision makes its accuracy much lower than fully supervised object detection (FSOD), and currently modern FSOD techniques cannot be applied to WSOD. To bridge the performance and technical gaps between WSOD and FSOD, this paper proposes a new framework, Salvage of Supervision (SoS), with the key idea being to harness every potentially useful supervisory signal in WSOD: the weak image-level labels, the pseudo-labels, and the power of semi-supervised object detection. This paper proposes new approaches to utilize these weak and noisy signals effectively, and shows that each type of supervisory signal brings in notable improvements, outperforms existing WSOD methods (which mainly use only the weak labels) by large margins. The proposed SoS-WSOD method also has the ability to freely use modern FSOD techniques. SoS-WSOD achieves 64.4 $m\text{AP}_{50}$ on VOC2007, 61.9 $m\text{AP}_{50}$ on VOC2012 and 16.6 $m\text{AP}_{50:95}$ on MS-COCO, and also has fast inference speed. Ablations and visualization further verify the effectiveness of SoS.
翻译:然而,由于缺乏捆绑箱监督,其准确性大大低于完全监督的物体探测(FSOD),而且目前现代FSOD技术无法应用于WSOD。为了缩小WSOD和FSOD之间的性能和技术差距,本文件提议了一个新的框架,即“监督保护”系统,其关键想法是利用WSOD中所有潜在有用的监督信号:微弱的图像级别标签、假标签和半监督的物体探测能力。本文件提出了有效利用这些薄弱和噪音信号的新办法,并表明每一种监督信号都带来了显著的改进,超越了现有的WSOD方法(主要使用弱的标签)的功能和技术差距。拟议的SS-SOD方法还能够自由使用现代FSOD技术。 SoS-SOD在VOC-2007上实现了64.4 $m\ text{AP ⁇ 50},61.9 $\ text{CO=50} 在VOC2012 和16.65 NSS 快速校验和 MS-S-50 速度。